Bridging satellite missions: deep transfer learning for enhanced tropical cyclone intensity estimation
Geostationary satellites are valuable tools for monitoring the entire lifetime of tropical cyclones (TCs). Although the most widely used method for TC intensity estimation is manual, several automatic methods, particularly artificial intelligence (AI)-based algorithms, have been proposed and have ac...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2024-12-01
|
| Series: | GIScience & Remote Sensing |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/15481603.2024.2325720 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846139011897229312 |
|---|---|
| author | Minki Choo Yejin Kim Juhyun Lee Jungho Im Il-Ju Moon |
| author_facet | Minki Choo Yejin Kim Juhyun Lee Jungho Im Il-Ju Moon |
| author_sort | Minki Choo |
| collection | DOAJ |
| description | Geostationary satellites are valuable tools for monitoring the entire lifetime of tropical cyclones (TCs). Although the most widely used method for TC intensity estimation is manual, several automatic methods, particularly artificial intelligence (AI)-based algorithms, have been proposed and have achieved significant performance. However, AI-based techniques often require large amounts of input data, making it challenging to adopt newly introduced data such as those from recently launched satellites. This study proposed a transfer-learning-based TC intensity estimation method to combine different source data. The pre-trained model was built using the Swin Transformer (Swin-T) model, utilizing data from the Communication Ocean and Meteorological Satellite Meteorological Imager sensor, which has been in operation for an extensive period (2011–2021) and provides a large dataset. Subsequently, a transfer learning model was developed by fine-tuning the pre-trained model using the GEO-KOMPSAT-2A Advanced Meteorological Imager, which has been operational since 2019. The transfer learning approach was tested in three different ways depending on the fine-tuning ratio, with the optimal performance achieved when all layers were fine-tuned. The pre-trained model employed TC observations from 2011 to 2017 for training and 2018 for testing, whereas the transfer learning model utilized data from 2019 and 2020 for training and 2021 for testing to evaluate the model performance. The best pre-trained and transfer learning models achieved mean absolute error of 6.46 kts and 6.48 kts, respectively. Our proposed model showed a 7–52% improvement compared to the control models without transfer learning. This implies that the transfer learning approach for TC intensity estimation using different satellite observations is significant. Moreover, by employing a deep learning model visualization approach known as Eigen-class activation map, the spatial characteristics of the developed model were validated according to the intensity levels. This analysis revealed features corresponding to the Dvorak technique, demonstrating the interpretability of the Swin-T-based TC intensity estimation algorithm. This study successfully demonstrated the effectiveness of transfer learning in developing a deep learning-based TC intensity estimation model for newly acquired data. |
| format | Article |
| id | doaj-art-f705ba3d5bb94acaaf7790cbd2db08e9 |
| institution | Kabale University |
| issn | 1548-1603 1943-7226 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | GIScience & Remote Sensing |
| spelling | doaj-art-f705ba3d5bb94acaaf7790cbd2db08e92024-12-06T13:51:50ZengTaylor & Francis GroupGIScience & Remote Sensing1548-16031943-72262024-12-0161110.1080/15481603.2024.2325720Bridging satellite missions: deep transfer learning for enhanced tropical cyclone intensity estimationMinki Choo0Yejin Kim1Juhyun Lee2Jungho Im3Il-Ju Moon4Department of Civil, Urban, Earth & Environmental Engineering, Ulsan National Institute of Science and Technology, Ulsan, Republic of KoreaDepartment of Civil, Urban, Earth & Environmental Engineering, Ulsan National Institute of Science and Technology, Ulsan, Republic of KoreaDepartment of Civil, Urban, Earth & Environmental Engineering, Ulsan National Institute of Science and Technology, Ulsan, Republic of KoreaDepartment of Civil, Urban, Earth & Environmental Engineering, Ulsan National Institute of Science and Technology, Ulsan, Republic of KoreaTyphoon Research Center, Jeju National University, Jeju, Republic of KoreaGeostationary satellites are valuable tools for monitoring the entire lifetime of tropical cyclones (TCs). Although the most widely used method for TC intensity estimation is manual, several automatic methods, particularly artificial intelligence (AI)-based algorithms, have been proposed and have achieved significant performance. However, AI-based techniques often require large amounts of input data, making it challenging to adopt newly introduced data such as those from recently launched satellites. This study proposed a transfer-learning-based TC intensity estimation method to combine different source data. The pre-trained model was built using the Swin Transformer (Swin-T) model, utilizing data from the Communication Ocean and Meteorological Satellite Meteorological Imager sensor, which has been in operation for an extensive period (2011–2021) and provides a large dataset. Subsequently, a transfer learning model was developed by fine-tuning the pre-trained model using the GEO-KOMPSAT-2A Advanced Meteorological Imager, which has been operational since 2019. The transfer learning approach was tested in three different ways depending on the fine-tuning ratio, with the optimal performance achieved when all layers were fine-tuned. The pre-trained model employed TC observations from 2011 to 2017 for training and 2018 for testing, whereas the transfer learning model utilized data from 2019 and 2020 for training and 2021 for testing to evaluate the model performance. The best pre-trained and transfer learning models achieved mean absolute error of 6.46 kts and 6.48 kts, respectively. Our proposed model showed a 7–52% improvement compared to the control models without transfer learning. This implies that the transfer learning approach for TC intensity estimation using different satellite observations is significant. Moreover, by employing a deep learning model visualization approach known as Eigen-class activation map, the spatial characteristics of the developed model were validated according to the intensity levels. This analysis revealed features corresponding to the Dvorak technique, demonstrating the interpretability of the Swin-T-based TC intensity estimation algorithm. This study successfully demonstrated the effectiveness of transfer learning in developing a deep learning-based TC intensity estimation model for newly acquired data.https://www.tandfonline.com/doi/10.1080/15481603.2024.2325720Tropical cyclonegeostationary meteorological satellitetransfer learningSwin Transformer |
| spellingShingle | Minki Choo Yejin Kim Juhyun Lee Jungho Im Il-Ju Moon Bridging satellite missions: deep transfer learning for enhanced tropical cyclone intensity estimation GIScience & Remote Sensing Tropical cyclone geostationary meteorological satellite transfer learning Swin Transformer |
| title | Bridging satellite missions: deep transfer learning for enhanced tropical cyclone intensity estimation |
| title_full | Bridging satellite missions: deep transfer learning for enhanced tropical cyclone intensity estimation |
| title_fullStr | Bridging satellite missions: deep transfer learning for enhanced tropical cyclone intensity estimation |
| title_full_unstemmed | Bridging satellite missions: deep transfer learning for enhanced tropical cyclone intensity estimation |
| title_short | Bridging satellite missions: deep transfer learning for enhanced tropical cyclone intensity estimation |
| title_sort | bridging satellite missions deep transfer learning for enhanced tropical cyclone intensity estimation |
| topic | Tropical cyclone geostationary meteorological satellite transfer learning Swin Transformer |
| url | https://www.tandfonline.com/doi/10.1080/15481603.2024.2325720 |
| work_keys_str_mv | AT minkichoo bridgingsatellitemissionsdeeptransferlearningforenhancedtropicalcycloneintensityestimation AT yejinkim bridgingsatellitemissionsdeeptransferlearningforenhancedtropicalcycloneintensityestimation AT juhyunlee bridgingsatellitemissionsdeeptransferlearningforenhancedtropicalcycloneintensityestimation AT junghoim bridgingsatellitemissionsdeeptransferlearningforenhancedtropicalcycloneintensityestimation AT iljumoon bridgingsatellitemissionsdeeptransferlearningforenhancedtropicalcycloneintensityestimation |